all AI news
Improving Membership Inference in ASR Model Auditing with Perturbed Loss Features
May 3, 2024, 4:53 a.m. | Francisco Teixeira, Karla Pizzi, Raphael Olivier, Alberto Abad, Bhiksha Raj, Isabel Trancoso
cs.LG updates on arXiv.org arxiv.org
Abstract: Membership Inference (MI) poses a substantial privacy threat to the training data of Automatic Speech Recognition (ASR) systems, while also offering an opportunity to audit these models with regard to user data. This paper explores the effectiveness of loss-based features in combination with Gaussian and adversarial perturbations to perform MI in ASR models. To the best of our knowledge, this approach has not yet been investigated. We compare our proposed features with commonly used error-based …
abstract arxiv asr audit automatic speech recognition combination cs.cr cs.lg cs.sd data eess.as features improving inference loss paper privacy recognition regard speech speech recognition systems threat training training data type user data while
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US